Sarvam AI
Sarvam

Sarvam Prism

System-1 decision model on Sarvam 105B. Typed yes/no, choice and score questions with a calibrated probability for every option—no text to parse.

  • Decisions
  • Calibrated probabilities
  • Indian languages

Best suited for

  1. 01

    Routing and triage

    Classify intents and route work using probability thresholds.

  2. 02

    Agent evaluation

    Judge runs, tool choice and which agent needs attention.

  3. 03

    Policy and scoring

    Run moderation, security checks and ordered severity scores.

Benchmarks

Prism leads Sarvam’s 25-model decision study on average score and Indian-language coverage.

Sarvam Prism evaluation ↗ · Published 3 November 2026.

Average across three decision indices

Index score
  • Sarvam Prism71.8
  • Perplexity Decider v1.268
  • Jev 1.1464.5
  • Clef62.6
  • Microsoft-Decision-161.1

Build with the Sarvam SDK

pip install -U "sarvamai>=0.1.43"V2 · Sarvam SDK · Decisions
import osfrom sarvamai import SarvamAI​client = SarvamAI(api_subscription_key=os.environ["SARVAM_API_KEY"])​response = client.decisions.create(    model="sarvam-prism",    state="My Stripe integration stopped working and all checkout payments are failing.",    questions={        "urgent": {            "type": "noul",            "instructions": "Is this urgent and revenue-impacting?"        },        "department": {            "type": "choice",            "instructions": "Which team should handle this?",            "criteria": {                "billing": "Payments or invoices",                "technical": "Bugs or outages",                "sales": "New business enquiries"            }        },        "severity": {            "type": "score",            "instructions": "Rate the severity.",            "criteria": [                "trivial",                "minor",                "moderate",                "major",                "critical"            ]        }    },)​department = response.answers["department"]top_probability = department.probabilities[department.choice]​if top_probability >= 0.9:    print("Route to", department.choice)else:    print("Send for review", department.probabilities)
  1. 01 Install the Sarvam SDK

    Install sarvamai (Python 0.1.43+ or JavaScript 1.1.15+). Store your key in SARVAM_API_KEY.

  2. 02 Call the Decisions API

    Send POST /v2/systemone with model ID sarvam-prism via client.decisions.create. The example sends one state and three typed questions.

  3. 03 Validate your application

    Check probabilities and thresholds on representative states. Route confident answers automatically and send uncertain ones to review before production traffic.

Model API Reference

Frequently Asked
Questions

Explore other models

View catalogue

From model choice to production. Bring your workload, traffic expectations and latency targets. Build on Sarvam’s serving stack in India.